Hwee Tou Ng
- Papers
- 14
Cite
Notes
Only stored in your browser.
Authored papers
14GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents
arXiv 2026
FocusUI: Efficient UI Grounding via Position-Preserving Visual Token Selection
arXiv 2026
The Hallucination Dilemma: Factuality-Aware Reinforcement Learning for Large Reasoning Models
arXiv 2025
SlideTailor: Personalized Presentation Slide Generation for Scientific Papers
arXiv 2025
Factorized Learning for Temporally Grounded Video-Language Models
arXiv 2025
Finding the Sweet Spot: Preference Data Construction for Scaling Preference Optimization
arXiv 2025
Just What You Desire: Constrained Timeline Summarization with Self-Reflection for Enhanced Relevance
arXiv 2024
Preference-Guided Reflective Sampling for Aligning Language Models
arXiv 2024
Multi-Agent Sampling: Scaling Inference Compute for Data Synthesis with Tree Search-Based Agentic Collaboration
arXiv 2024
Self-Judge: Selective Instruction Following with Alignment Self-Evaluation
arXiv 2024
Think&Cite: Improving Attributed Text Generation with Self-Guided Tree Search and Progress Reward Modeling
arXiv 2024
Towards Benchmarking and Improving the Temporal Reasoning Capability of Large Language Models
arXiv 2023
System Combination via Quality Estimation for Grammatical Error Correction
arXiv 2023
Revisiting DocRED -- Addressing the False Negative Problem in Relation Extraction
arXiv 2022
Affiliations
Frequent co-authors
10from 14 papers